Upload Date | September 18 2024 10:10 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone 15 Plus |
Model ID | iPhone15,5 |
Motherboard | D38AP |
CPU Information | |
---|---|
Name | Apple A16 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.46 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.53 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1449
269.5 IPS |
|
Image Classification (HP)
|
100% |
10434
1.94 KIPS |
|
Image Classification (Q)
|
97% |
12576
2.35 KIPS |
|
Image Segmentation (SP)
|
100% |
1474
23.9 IPS |
|
Image Segmentation (HP)
|
100% |
11778
190.9 IPS |
|
Image Segmentation (Q)
|
99% |
12790
207.3 IPS |
|
Pose Estimation (SP)
|
100% |
6938
8.10 IPS |
|
Pose Estimation (HP)
|
100% |
100391
117.1 IPS |
|
Pose Estimation (Q)
|
95% |
102127
119.7 IPS |
|
Object Detection (SP)
|
100% |
1609
127.6 IPS |
|
Object Detection (HP)
|
100% |
12902
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14396
1.15 KIPS |
|
Face Detection (SP)
|
100% |
3249
38.6 IPS |
|
Face Detection (HP)
|
100% |
30740
365.3 IPS |
|
Face Detection (Q)
|
100% |
38298
455.1 IPS |
|
Depth Estimation (SP)
|
100% |
6331
48.8 IPS |
|
Depth Estimation (HP)
|
99% |
76101
586.3 IPS |
|
Depth Estimation (Q)
|
85% |
94711
740.5 IPS |
|
Style Transfer (SP)
|
100% |
18648
24.0 IPS |
|
Style Transfer (HP)
|
100% |
175088
225.1 IPS |
|
Style Transfer (Q)
|
96% |
173143
223.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4217
155.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
32276
1.19 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37290
1.38 KIPS |
|
Text Classification (SP)
|
100% |
2623
3.50 KIPS |
|
Text Classification (HP)
|
100% |
2255
3.01 KIPS |
|
Text Classification (Q)
|
93% |
2104
2.82 KIPS |
|
Machine Translation (SP)
|
100% |
3445
59.3 IPS |
|
Machine Translation (HP)
|
100% |
2318
39.9 IPS |
|
Machine Translation (Q)
|
98% |
2341
40.5 IPS |